aiqbench analysis
This research introduces a preference-conditioned reinforcement learning framework that enables real-time tuning of transit signal priority without retraining, effectively balancing bus efficiency against general traffic flow constraints. By leveraging IntersectionZoo and augmented scenario generation, the study demonstrates how dynamic policy adjustments can outperform static rule-based systems while maintaining operational feasibility under varying agency priorities.
Preference-Conditioned Multi-Objective Reinforcement Learning for Runtime-Tunable Transit Signal Priority
arXiv:2607.18286v1 Announce Type: cross Abstract: Transit signal priority (TSP) requires balancing competing objectives: reducing bus delay while limiting adverse impacts on non-bus traffic and avoiding extreme waits for a subset of vehicles. Existing reinforcement-learning (RL) approaches to TSP typically encode transit-aware features (e.g., occupancy and schedule deviation) but optimize a fixed reward or fixed scalarization, which limits operational flexibility when agency priorities change across time-of-day or disruption conditions. We present a preference-conditioned TSP controller, $\pi(a \mid s,w)$, that selects the next signal phase under minimum/maximum green and transition-feasibility constraints and can be tuned at runtime via a preference parameter $w$ to trade off bus-priority emphasis against overall traffic delay without retraining. We implement this on top of IntersectionZoo by introducing a constrained signal-control/TSP wrapper, and we extend scenario generation with bus-prevalence augmentation and timetable-based bus insertion to address sparse transit-priority events during training. Experiments against fixed-time control, a rule-based TSP overlay, and fixed-weight PPO specialists show that a single learned conditioned policy spans a smooth empirical trade-off frontier across runtime preferences, outperforms fixed-time and rule-based baselines, and maintains constraint feasibility, while tail-delay diagnostics reveal that non-bus externalities remain limited for moderate preference settings but can increase substantially under high bus-priority weights. The source code of this work is available at https://github.com/urbanAIthi/morl-tsp.
Abstract:Transit signal priority (TSP) requires balancing competing objectives: reducing bus delay while limiting adverse impacts on non-bus traffic and avoiding extreme waits for a subset of vehicles. Existing reinforcement-learning (RL) approaches to TSP typically encode transit-aware features (e.g., occupancy and schedule deviation) but optimize a fixed reward or fixed scalarization, which limits operational flexibility when agency priorities change across time-of-day or disruption conditions. We present a preference-conditioned TSP controller, $\pi(a \mid s,w)$, that selects the next signal phase under minimum/maximum green and transition-feasibility constraints and can be tuned at runtime via a preference parameter $w$ to trade off bus-priority emphasis against overall traffic delay without retraining. We implement this on top of IntersectionZoo by introducing a constrained signal-control/TSP wrapper, and we extend scenario generation with bus-prevalence augmentation and timetable-based bus insertion to address sparse transit-priority events during training. Experiments against fixed-time control, a rule-based TSP overlay, and fixed-weight PPO specialists show that a single learned conditioned policy spans a smooth empirical trade-off frontier across runtime preferences, outperforms fixed-time and rule-based baselines, and maintains constraint feasibility, while tail-delay diagnostics reveal that non-bus externalities remain limited for moderate preference settings but can increase substantially under high bus-priority weights. The source code of this work is available at this https URL.
8 pages, 3 figures, 4 tables. Accepted at the 29th IEEE International Conference on Intelligent Transportation Systems (ITSC 2026). Code: this https URL
Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Systems and Control (eess.SY)
arXiv:2607.18286 [cs.LG]
(or arXiv:2607.18286v1 [cs.LG] for this version)
Full text under the publisher's open licence · 249 words
Related coverage
PROMO: Preference-conditioned Multi-Objective Reinforcement Learning for Quadrupedal Robots
arXiv · Oct 2, 2026
ORACLE: A Multi-Objective Reinforcement Learning-Based Analog Circuit Design Optimizer with Large Language Models-Guided Exploration
arXiv · Aug 6, 2026
Build a Physical AI model factory with NVIDIA Cosmos 3 on SageMaker HyperPod
AWS · Sep 4, 2026
Emotional Preferences as Goal-Priority Regulation
arXiv · Aug 28, 2026